Back to search

Georgia Institute of Technology

Mitigating Racial Biases in Toxic Language Detection

Abstract

dc:description.abstract

Recent research has demonstrated how racial biases against users who write African American English exists in popular toxic language datasets. While previous work has focused on a single fairness criteria, we propose to use additional descriptive fairness metrics to better understand the source of these biases. We demonstrate that different benchmark classifiers, as well as two in-process bias-remediation techniques, propagate racial biases even in a larger corpus. We then propose a novel ensemble-framework that uses a specialized classifier that is fine-tuned to the African American English dialect. We show that our proposed framework substantially reduces the racial biases that the model learns from these datasets. We demonstrate how the ensemble framework improves fairness metrics across all sample datasets with minimal impact on the classification performance, and provide empirical evidence to its ability to unlearn the annotation biases towards authors who use African American English. ** Please note that this work may contain examples of offensive words and phrases.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Computer Science
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Halevy, Matan
Advisor dc:contributor.advisor
  • Howard, Ayanna M.
Committee members dc:contributor.committeemember
  • Bruckman, Amy
  • Yang, Diyi

Subjects

dc:subject × 4

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
http://hdl.handle.net/1853/66502

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Halevy, Matan. Mitigating Racial Biases in Toxic Language Detection. Masters thesis, Georgia Institute of Technology, 2022. http://hdl.handle.net/1853/66502